#inference-acceleration Repositories
Discover 14 active open source GitHub repositories tagged with #inference-acceleration, accumulating 24,811 total stars (averaging 1,772 stars per project). Leading this topic is openai/consistency_models with 6,461 stars.
14 repositories total
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
A batched offline inference oriented version of segment-anything
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
SparkDiffusion: Accelerating DiT video generation by 265ร via joint sparsity, distillation, quantization, etc.
[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable SparseโLinear Attention
Frequently Asked Questions
What is the most popular #inference-acceleration repository on GitHub?
The top ranked open source #inference-acceleration project on GitHub is openai/consistency_models with 6,461 stars. Official repo for consistency models.
Which programming languages are most used in #inference-acceleration repositories?
Among the top ranked #inference-acceleration projects on GitHub, the most common programming languages are Python, Cuda.
How is the #inference-acceleration repository ranking calculated?
We track 14 active open source repositories tagged with #inference-acceleration (500+ stars), totaling 24,811 stars with an average of 1,772 stars per repository. Rankings update daily from the GitHub API.